INSTALL.txt

Repository Structure:
This repository can broadly be divided into two parts: the Notebooks, 
and the *.py scripts. Both the parts contain the same matter, however, the
use of Notebooks is suggested as it is easier to understand and follow.

INSTALLATION and RUNNING :

for using the NOTEBOOKS, refer to 
http://bookwormankur.blogspot.se/2013/07/mid-term-summary-part-5-using-notebooks.html

for the *.py scripts, download and run as python NAME.py <options - if needed>. 
Make sure to change the directory as per your need. The default directory is set to D:/Dropbox/Ankur/...
Also, each subfolder in the repository contains README specific to the scripts.

Teseract 3.0x is NOT included in the repository. 
Install it separately from https://code.google.com/p/tesseract-ocr/

ImageMagick is used in last leg of the data generation script. 
Install it from http://www.imagemagick.org/script/index.php 

for a list of requirements, refer to 
http://bookwormankur.blogspot.se/2013/07/mid-term-summary-part-2-shaping-bookworm.html